使用Javascript的atob解码base64不能正确解码utf-8字符串

我使用Javascript window.atob()函数来解码base64编码的字符串(特别是来自GitHub API的base64编码的内容)。问题是我得到ascii编码的字符返回(如âⅱ而不是™)。我如何正确地处理传入的base64编码流，以便将其解码为utf-8?

当前回答

解码base64到UTF8字符串

以下是@brandonscript目前投票最多的答案

function b64DecodeUnicode(str) {
    // Going backwards: from bytestream, to percent-encoding, to original string.
    return decodeURIComponent(atob(str).split('').map(function(c) {
        return '%' + ('00' + c.charCodeAt(0).toString(16)).slice(-2);
    }).join(''));
}

上面的代码可以工作，但是非常慢。如果您的输入是一个非常大的base64字符串，例如，对于一个base64 html文档，30,000个字符。这需要大量的计算。

这是我的答案，使用内置的TextDecoder，比上面的大输入代码快近10倍。

function decodeBase64(base64) {
    const text = atob(base64);
    const length = text.length;
    const bytes = new Uint8Array(length);
    for (let i = 0; i < length; i++) {
        bytes[i] = text.charCodeAt(i);
    }
    const decoder = new TextDecoder(); // default is utf-8
    return decoder.decode(bytes);
}

2020-11-09 13:09:48

其他回答

对我有用的完整文章:https://developer.mozilla.org/en-US/docs/Web/JavaScript/Base64_encoding_and_decoding

我们从Unicode/UTF-8编码的部分是

function utf8_to_b64( str ) {
   return window.btoa(unescape(encodeURIComponent( str )));
}

function b64_to_utf8( str ) {
   return decodeURIComponent(escape(window.atob( str )));
}

// Usage:
utf8_to_b64('✓ à la mode'); // "4pyTIMOgIGxhIG1vZGU="
b64_to_utf8('4pyTIMOgIGxhIG1vZGU='); // "✓ à la mode"

这是当今最常用的方法之一。

2020-06-23 14:51:15

I would assume that one might want a solution that produces a widely useable base64 URI. Please visit data:text/plain;charset=utf-8;base64,4pi44pi54pi64pi74pi84pi+4pi/ to see a demonstration (copy the data uri, open a new tab, paste the data URI into the address bar, then press enter to go to the page). Despite the fact that this URI is base64-encoded, the browser is still able to recognize the high code points and decode them properly. The minified encoder+decoder is 1058 bytes (+Gzip→589 bytes)

!function(e){"use strict";function h(b){var a=b.charCodeAt(0);if(55296<=a&&56319>=a)if(b=b.charCodeAt(1),b===b&&56320<=b&&57343>=b){if(a=1024*(a-55296)+b-56320+65536,65535<a)return d(240|a>>>18,128|a>>>12&63,128|a>>>6&63,128|a&63)}else return d(239,191,189);return 127>=a?inputString:2047>=a?d(192|a>>>6,128|a&63):d(224|a>>>12,128|a>>>6&63,128|a&63)}function k(b){var a=b.charCodeAt(0)<<24,f=l(~a),c=0,e=b.length,g="";if(5>f&&e>=f){a=a<<f>>>24+f;for(c=1;c<f;++c)a=a<<6|b.charCodeAt(c)&63;65535>=a?g+=d(a):1114111>=a?(a-=65536,g+=d((a>>10)+55296,(a&1023)+56320)):c=0}for(;c<e;++c)g+="\ufffd";return g}var m=Math.log,n=Math.LN2,l=Math.clz32||function(b){return 31-m(b>>>0)/n|0},d=String.fromCharCode,p=atob,q=btoa;e.btoaUTF8=function(b,a){return q((a?"\u00ef\u00bb\u00bf":"")+b.replace(/[\x80-\uD7ff\uDC00-\uFFFF]|[\uD800-\uDBFF][\uDC00-\uDFFF]?/g,h))};e.atobUTF8=function(b,a){a||"\u00ef\u00bb\u00bf"!==b.substring(0,3)||(b=b.substring(3));return p(b).replace(/[\xc0-\xff][\x80-\xbf]*/g,k)}}(""+void 0==typeof global?""+void 0==typeof self?this:self:global)

下面是用于生成它的源代码。

var fromCharCode = String.fromCharCode;
var btoaUTF8 = (function(btoa, replacer){"use strict";
    return function(inputString, BOMit){
        return btoa((BOMit ? "\xEF\xBB\xBF" : "") + inputString.replace(
            /[\x80-\uD7ff\uDC00-\uFFFF]|[\uD800-\uDBFF][\uDC00-\uDFFF]?/g, replacer
        ));
    }
})(btoa, function(nonAsciiChars){"use strict";
    // make the UTF string into a binary UTF-8 encoded string
    var point = nonAsciiChars.charCodeAt(0);
    if (point >= 0xD800 && point <= 0xDBFF) {
        var nextcode = nonAsciiChars.charCodeAt(1);
        if (nextcode !== nextcode) // NaN because string is 1 code point long
            return fromCharCode(0xef/*11101111*/, 0xbf/*10111111*/, 0xbd/*10111101*/);
        // https://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae
        if (nextcode >= 0xDC00 && nextcode <= 0xDFFF) {
            point = (point - 0xD800) * 0x400 + nextcode - 0xDC00 + 0x10000;
            if (point > 0xffff)
                return fromCharCode(
                    (0x1e/*0b11110*/<<3) | (point>>>18),
                    (0x2/*0b10*/<<6) | ((point>>>12)&0x3f/*0b00111111*/),
                    (0x2/*0b10*/<<6) | ((point>>>6)&0x3f/*0b00111111*/),
                    (0x2/*0b10*/<<6) | (point&0x3f/*0b00111111*/)
                );
        } else return fromCharCode(0xef, 0xbf, 0xbd);
    }
    if (point <= 0x007f) return nonAsciiChars;
    else if (point <= 0x07ff) {
        return fromCharCode((0x6<<5)|(point>>>6), (0x2<<6)|(point&0x3f));
    } else return fromCharCode(
        (0xe/*0b1110*/<<4) | (point>>>12),
        (0x2/*0b10*/<<6) | ((point>>>6)&0x3f/*0b00111111*/),
        (0x2/*0b10*/<<6) | (point&0x3f/*0b00111111*/)
    );
});

然后，要解码base64数据，HTTP可以将数据作为数据URI获取，也可以使用下面的函数。

var clz32 = Math.clz32 || (function(log, LN2){"use strict";
    return function(x) {return 31 - log(x >>> 0) / LN2 | 0};
})(Math.log, Math.LN2);
var fromCharCode = String.fromCharCode;
var atobUTF8 = (function(atob, replacer){"use strict";
    return function(inputString, keepBOM){
        inputString = atob(inputString);
        if (!keepBOM && inputString.substring(0,3) === "\xEF\xBB\xBF")
            inputString = inputString.substring(3); // eradicate UTF-8 BOM
        // 0xc0 => 0b11000000; 0xff => 0b11111111; 0xc0-0xff => 0b11xxxxxx
        // 0x80 => 0b10000000; 0xbf => 0b10111111; 0x80-0xbf => 0b10xxxxxx
        return inputString.replace(/[\xc0-\xff][\x80-\xbf]*/g, replacer);
    }
})(atob, function(encoded){"use strict";
    var codePoint = encoded.charCodeAt(0) << 24;
    var leadingOnes = clz32(~codePoint);
    var endPos = 0, stringLen = encoded.length;
    var result = "";
    if (leadingOnes < 5 && stringLen >= leadingOnes) {
        codePoint = (codePoint<<leadingOnes)>>>(24+leadingOnes);
        for (endPos = 1; endPos < leadingOnes; ++endPos)
            codePoint = (codePoint<<6) | (encoded.charCodeAt(endPos)&0x3f/*0b00111111*/);
        if (codePoint <= 0xFFFF) { // BMP code point
          result += fromCharCode(codePoint);
        } else if (codePoint <= 0x10FFFF) {
          // https://mathiasbynens.be/notes/javascript-encoding#surrogate-formulae
          codePoint -= 0x10000;
          result += fromCharCode(
            (codePoint >> 10) + 0xD800,  // highSurrogate
            (codePoint & 0x3ff) + 0xDC00 // lowSurrogate
          );
        } else endPos = 0; // to fill it in with INVALIDs
    }
    for (; endPos < stringLen; ++endPos) result += "\ufffd"; // replacement character
    return result;
});

更标准的优点是这个编码器和这个解码器更广泛地适用，因为它们可以用作正确显示的有效URL。观察。

In addition to being very standardized, the above code snippets are also very fast. Instead of an indirect chain of succession where the data has to be converted several times between various forms (such as in Riccardo Galli's response), the above code snippet is as direct as performantly possible. It uses only one simple fast String.prototype.replace call to process the data when encoding, and only one to decode the data when decoding. Another plus is that (especially for big strings), String.prototype.replace allows the browser to automatically handle the underlying memory management of resizing the string, leading a significant performance boost especially in evergreen browsers like Chrome and Firefox that heavily optimize String.prototype.replace. Finally, the icing on the cake is that for you latin script exclūsīvō users, strings which don't contain any code points above 0x7f are extra fast to process because the string remains unmodified by the replacement algorithm.

我已经在https://github.com/anonyco/BestBase64EncoderDecoder/为这个解决方案创建了一个github存储库

2018-11-22 14:52:26

包括上述解决方案，如果仍然面临问题，尝试如下，考虑转义不支持TS的情况。

blob = new Blob(["\ufeff", csv_content]); // this will make symbols to appears in excel

对于csv_content，您可以像下面这样尝试。

function b64DecodeUnicode(str: any) {        
        return decodeURIComponent(atob(str).split('').map((c: any) => {
            return '%' + ('00' + c.charCodeAt(0).toString(16)).slice(-2);
        }).join(''));
    }

2018-08-08 09:47:30

以下是Mozilla开发资源中描述的2018年更新的解决方案

从unicode编码到b64

function b64EncodeUnicode(str) {
    // first we use encodeURIComponent to get percent-encoded UTF-8,
    // then we convert the percent encodings into raw bytes which
    // can be fed into btoa.
    return btoa(encodeURIComponent(str).replace(/%([0-9A-F]{2})/g,
        function toSolidBytes(match, p1) {
            return String.fromCharCode('0x' + p1);
    }));
}

b64EncodeUnicode('✓ à la mode'); // "4pyTIMOgIGxhIG1vZGU="
b64EncodeUnicode('\n'); // "Cg=="

从b64解码到unicode

function b64DecodeUnicode(str) {
    // Going backwards: from bytestream, to percent-encoding, to original string.
    return decodeURIComponent(atob(str).split('').map(function(c) {
        return '%' + ('00' + c.charCodeAt(0).toString(16)).slice(-2);
    }).join(''));
}

b64DecodeUnicode('4pyTIMOgIGxhIG1vZGU='); // "✓ à la mode"
b64DecodeUnicode('Cg=='); // "\n"

2018-10-04 13:02:27